Finite-sample based learning algorithms for feedforward networks
Conference
·
OSTI ID:43785
- Oak Ridge National Lab., TN (United States)
- Louisiana State Univ., Baton Rouge, LA (United States). Dept. of Computer Science
We discuss two classes of convergent algorithms for learning continuous functions (and also regression functions) that are represented by FeedForward Networks (FFN). The first class of algorithms, applicable to networks with unknown weights located only in the output layer, is obtained by utilizing the potential function methods of Aizerman et al. The second class, applicable to general feedforward networks, is obtained by utilizing the classical Robbins-Monro style stochastic approximation methods. Conditions relating the sample sizes to the error bounds are derived for both classes of algorithms using martingale-type inequalities. For concreteness, the discussion is presented in terms of neural networks, but the results are applicable to general feedforward networks, in particular to wavelet networks. The algorithms can also be directly applied to concept learning problems. A main distinguishing feature of the this work is that the sample sizes are based on explicit algorithms rather than information-based methods.
- Research Organization:
- Oak Ridge National Lab., TN (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- AC05-84OR21400
- OSTI ID:
- 43785
- Report Number(s):
- CONF-9505145--2; ON: DE95009123
- Country of Publication:
- United States
- Language:
- English
Similar Records
Learning algorithms for feedforward networks based on finite samples
PAC learning algorithms for functions approximated by feedforward networks
On stochastic approximation algorithms for classes of PAC learning problems
Technical Report
·
Thu Sep 01 00:00:00 EDT 1994
·
OSTI ID:10190716
PAC learning algorithms for functions approximated by feedforward networks
Conference
·
Sat Jun 01 00:00:00 EDT 1996
·
OSTI ID:244610
On stochastic approximation algorithms for classes of PAC learning problems
Conference
·
Mon Feb 28 23:00:00 EST 1994
·
OSTI ID:10128931